© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11051
    Prev
    Next
    INDEX
    Explanations

    posted by or on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Äijiá»ĥn
    -0.09
    ìĬĪ
    -0.09
    æµľ
    -0.09
    ç§ķ
    -0.08
    ège
    -0.08
    é»ĺé»ĺåľ°
    -0.08
     smash
    -0.08
    /mit
    -0.08
    istic
    -0.08
    ESC
    -0.08
    POSITIVE LOGITS
    pone
    0.12
    GRES
    0.10
    kest
    0.10
    idon
    0.10
    lights
    0.09
    é«»
    0.09
    greSQL
    0.09
    itive
    0.09
    coc
    0.09
    ion
    0.09
    Activations Density 0.038%

    No Known Activations